Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is Gemma 4 31B IT?

104 SI-IQ · 90% interval 98–110
Not ranked: too little data

Gemma 4 31B IT is a model from Google DeepMind, released on Apr 2, 2026. Its SI-IQ is 104 (90% interval 98–110), estimated from 4 benchmark results by 2 independent evaluators.

This model has fewer than 5 independent benchmark results or fewer than 2 different evaluators, so it is shown but not ranked.

Facts

Developer: Google DeepMind
Released: Apr 2, 2026
Access: Open weights (restricted licence)
Benchmarks used: 4 results from 2 evaluators

Ability by area (SI-IQ, 90% interval)

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark	Area	Score	Implied SI-IQ	Evaluated by	As listed by the source	Retrieved	Source
OTIS Mock AIME 2024–2025	Math	73.3%	104	Epoch AI	`gemma-4-31b-it_minimal`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond	Knowledge	75.8%	102	Epoch AI	`gemma-4-31b-it_minimal`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run)	Knowledge	81.6%	113	OpenRouter	`google/gemma-4-31b-it-20260402` CoreWeave · median over providers (10 of 10 rows), lower median	Oct 18, 2026	OpenRouter benchmark datasets · data file
SimpleQA Verified	Knowledge	10.4%	77	Epoch AI	`gemma-4-31b-it`	Oct 18, 2026	Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run)	Agents	75.7%	130	OpenRouter	`google/gemma-4-31b-it-20260402` Cerebras, Chutes, CoreWeave, Crusoe, DeepInfra, Friendli, ModelRun, Morph, Novita, OpenInference, Parasail, Phala, SambaNova, SiliconFlow, Venice · median over providers (15 of 15 rows)	Oct 18, 2026	OpenRouter benchmark datasets · data file

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter..